{"title":"Implementation of Self-Attention-based 2D CNN Models for Enhancing Remaining Useful Life Predictions Using Multivariate Time Series Data","authors":"Min-Seok Baek, Jae-Pil Ban","doi":"10.33162/jar.2023.8.23.3.238","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.238","url":null,"abstract":"Purpose: This research aims to introduce a novel a methodology for predicting the Remaining Useful Life (RUL) using multivariate time series data.BRMethods: The proposed RUL prediction methodology comprises of the following steps: 1) Reorganizing the multivariate time series data to enhance the correlation between different time series datasets; 2) Streamlining various time series data into a single pixel utilizing 2D convolutional layers; 3) Emphasizing the substantial correlation among different time series using a self-attention layer; 4) Estimating the RUL with Bi-LSTM and fully connected layers.BRResults: In comparison with existing deep learning models utilizing the identical test datasets, the proposed model exhibits greater performance in RUL prediction. A detailed analysis reveals the model’s merits in terms of data reorganization alongside the application of 2D CNN and multi-head self attention layers in the RUL prediction.BRConclusion: The proposed model provides more accurate RUL estimation results relative to pre-existing models using multivariate datasets obtained from multiple sensors, showing promising potential for its use in real-world applications.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jinhong Bang, Youngjin Je, Taeyoung Yoon, Jaehyeok Doh
{"title":"Accelerated Life Testing Data-Based Lifetime Prediction of Rubber Material for Bushing Using Global-Local Optimization Technique","authors":"Jinhong Bang, Youngjin Je, Taeyoung Yoon, Jaehyeok Doh","doi":"10.33162/jar.2023.8.23.3.211","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.211","url":null,"abstract":"Objective: This research aims to devise a predictive method for assessing the lifespan and dependability of rubber materials employed in automotive suspension systems. This study intends to improve product dependability, and design verification by evaluating the degradation patterns of these materials under accelerated testing.BRMethods: An accelerated life test was conducted, subjecting materials to different temperature and time conditions. Degradation behavior was determined by applying global-local optimization techniques and selecting an appropriate degradation model. The Arrhenius equation (k = A·exp (−ESUBa/SUB/RT)), was used in regression analysis to forecast the lifespan of the material under typical temperature conditions.BRResults: The model’s reliability is assessed through the coefficient of determination and mean squared error. As optimization advances, predictions become more reliable and are confirmed by a coefficient of determination exceeding a 99% confidence level.BRConclusion: Predictive approaches for estimating the lifespan and dependability of rubber materials in automotive suspension systems facilitate early-stage validation, enhancing product reliability and, minimizing failure expenses.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heewook Kim, Seongjun Im, Junghwan Yoon, Jaehoon Lim, Sejoon Jang
{"title":"Development of a Training Platform based on Hazard Analysis","authors":"Heewook Kim, Seongjun Im, Junghwan Yoon, Jaehoon Lim, Sejoon Jang","doi":"10.33162/jar.2023.8.23.3.221","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.221","url":null,"abstract":"Purpose: In the development of weapon systems, it is essential to develop CBT (Computer-Based Training) as an educational and training tool. To maximize the effectiveness of training, we propose a method for selecting core training content to conduct preliminary learning for dangerous incidents that may occur during the operation of weapon systems. Additionally, we propose a plan for developing a training platform for creating content and conducting training based on virtual reality.BRMethods: Based on the types of mitigation measures derived from the hazard analysis, we establish the criteria for selecting educational training content. We suggest a training platform that develops a server-client platform, allowing multiple trainees to simultaneously access and conduct virtual reality-based training and manage the content themselves.BRResults: If the scenario needs modification, the trainees can directly modify, add, or delete the scenario using the training platform. Moreover, new training content can be customized. Additionally, by managing the results of the weapon system","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Meta Island Reliability Study Using Digital Twin Technology","authors":"Euncheol Jeong, Seungwan Lim, Jaehoon Bae","doi":"10.33162/jar.2023.8.23.3.297","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.297","url":null,"abstract":"Purpose: This study aims to assess the feasibility of a virtual “meta island” for the development of future digital technology advancements. Feasibility will be determined by optimizing large-capacity data and creating a virtual meta island using digital twin and AI technologies.BRMethods: After acquiring the necessary data to create a 3D virtual model of the island using Metrix camera, drone, and 3D scanning technologies, the reliability of the meta island was analyzed through the optimization of the acquired data.BRResults: A 3D virtual island model can be created using digital twin technology and subsequently used as a test bed to derive original spatial structures.BRConclusion: The meta island is the first project to combine metaverse, digital twin, and AI technologies. It may provide future opportunities to export metaverse technology globally and to establish practical ways to improve the new virtual island environment for its citizens.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Sensitivity Analysis for Cost Optimization of Software Reliability Growth Model with Multiple Change Points","authors":"Dae-kyung Kim","doi":"10.33162/jar.2023.8.23.3.305","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.305","url":null,"abstract":"Purpose: It is recommended to complete the testing of a software and release it to maintain its market growth, and lower development research costs are critical for software developers. In this paper, we consider the optimal release time to be achieved when the program development cost is minimized in a model that has a bathtub-shaped failure detection rate with a change point. Here, we identify the various parameters that significantly affect the release time.BRMethods: Considering the cost function of the average failure function for this model, we aimed to estimate the release time to minimize it, to observe the changes in the release time when a parameter changes around the time of release, and to find a parameter that significantly affects the release time.BRResults: The values of the parameters α, λ, Φ and γ₁ continuously increased, and the total cost C(T) decreased and affected the release time T . Further, as the values of the parameters and increased, the total cost γ₃ and release time C(T) do not appear to have an effect.BRConclusion: In this paper, the optimal release time was obtained by considering the cost function for the reliability growth model with a bathtub-shaped failure detection melting with a change point, and the effect on the release time was investigated as each parameter changed. Since the parameters formulated based on the initial data collected are generally inaccurate, it is important to determine the sensitivity.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of Life Prediction Model and Accelerated No-Failure Test Method for Durability Test of Door Module Rear","authors":"Yun-Cheol Kim, Kyung-Min Choi","doi":"10.33162/jar.2023.8.23.3.256","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.256","url":null,"abstract":"Purpose: The purpose of this study is to develop the Life Prediction Model of the Door Module Rear and to propose the Test Time applied with the accelerated failure-free test method.BRMethods: By analyzing field failures, the failure mode and failure mechanism were selected. The type and level of stress that causes the failure mechanism were selected. An accelerated life test was conducted, and life was analyzed based on the test results. By estimating the shape parameter, β, and the voltage constant, n, the Test Time was calculated by the No-Failure Test Method. Finally, The Acceleration Factor under high stress condition was derived using a Life Prediction Model, and the Test Time under high stress condition was derived using the Acceleration Factor.BRResults: The failure mechanism for the test results and field failure were the same. Life was analyzed to estimate the parameters of the Life Distribution and Life Prediction Model.BRConclusion: The Test Time under high stress condition was calculated using the No-Failure Test Method and the Acceleration Factor, and the effect of shortening the Test Time was obtained. Results show that the efficiency in terms of time and cost for the Durability Test of the Door Module Rear was increased.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prognostics and Health Management using Artificial Intelligence","authors":"Jaiwook Baik","doi":"10.33162/jar.2023.8.23.3.283","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.283","url":null,"abstract":"Purpose: This study aims to examine artificial intelligence (AI) algorithms used in prognostics and health management (PHM), present a C-MAPPS data case study from the PHM competition, and identify the further research needed in AI-based PHM.BRMethod: AI algorithms that are widely used in PHM are machine learning (ML) methodologies such as ANN, SVM, DT, and kNN. In this study, we briefly introduced these methods and applied them to the C-MAPPS data presented in the PHM competition.BRResults: An organized series of procedures is needed to utilize AI in PHM. This study presented the proper procedure for using AI in PHM, explaining the necessity of training it with data using ML methodologies and verifying it with verification data.BRConclusion: The recent development of ML has been spreading PHM across industries, coupled with condition-based maintenance, one of the reliability strategies. In this study, we applied ML methodologies, including kNN, SVM, random forest, and LSTM, to the C-MAPPS data and discovered that kNN showed slightly better results than the other models in the data presented.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ye-Eun Jeong, Kihyun Kim, Hyun-Su Sim, Jong-Woo Park, Yong-Soo Kim
{"title":"Research on Advancing Test Procedures for Metal Detection Equipment","authors":"Ye-Eun Jeong, Kihyun Kim, Hyun-Su Sim, Jong-Woo Park, Yong-Soo Kim","doi":"10.33162/jar.2023.8.23.3.261","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.261","url":null,"abstract":"Purpose: This study aims to improve airport metal detection performance and clarify safety requirements, introducing a new method for electromagnetic wave measurement.BRMethods: Performance certification requirements were compared with Korean Ministry of Land, Infrastructure, and Transport","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Formulating Risk Indices and Criteria for Unmanned Aerial Systems","authors":"Hyunjung Cho, Dooyoul Lee","doi":"10.33162/jar.2023.8.23.3.229","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.229","url":null,"abstract":"Purpose: Owing to widespread use of unmanned aerial systems (UAS) across various sectors, the likelihood of accidents is progressively increasing. To ensure operational safety and reliability, establishing risk indices and criteria is imperative. However, current insufficient accident data hinder the formulation of reliable risk criteria. Thus, this study offers a proposition for UAS risk indices, prioritizing ground personnel damage as a significant consequence of UAS crashes.BRMethods: The comprehension of major risk events influencing factors, treated probabilistically, enables the derivation of risk indices and criteria for UAS. These get established through comparison with the risk indices and criteria for conventional manned aerial systems‘ structures and engines, including factors like Single Flight Probability of Failure (SFPOF), Cumulative Probability of Failure (CPOF), Non-Recoverable In-Flight Engine Shutdown (NRIFSD) and Engine Related Loss of Aircraft (ERLOA).BRResults: The risk criteria for UAS can be updated by referencing risk indices (NRIFSD, ERLOA) based on instantaneous or cumulative failure rates of manned aerial systems. Both rates take into account the risk severities and the occurrence probabilities for each risk factor. Notably, the specific acceptable risk criteria for UAS can be appropriately adjusted by considering the likelihood of a fatal injury to ground personnel (0.01∼1) and the probability of a person‘s proximity to the UAS crash site (0.026∼0.000019 people/m2) according to the operational environment.BRConclusion: NRIFSD, representing risk per 100,000 hours, suits short-term operations’ risk evaluation. Concurrently, ERLOA provides comprehensive information about the reliability of the aircraft, enabling its utilization in managing operational maintenance costs and making economic lifespan decisions. Depending on the operational environment and UAS objectives of, users can select appropriate risk indices and criteria.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jongchan Lee, Sungchul Ha, Seungjin Han, Jae-Hak Lim
{"title":"Reliability Performance Management Method for Weapons Under Development Based On a Reliability Scorecard","authors":"Jongchan Lee, Sungchul Ha, Seungjin Han, Jae-Hak Lim","doi":"10.33162/jar.2023.8.23.3.272","DOIUrl":"https://doi.org/10.33162/jar.2023.8.23.3.272","url":null,"abstract":"Purpose: The reliability of products produced by domestic companies has been inefficiently managed because of various challenges faced by these companies in product development and production. In addition, the defense industry lacks systematic reliability management activities during weapon system development. This study proposes an effective procedure for managing the reliability performance of weapon systems during their development.BRMethods: We analyzed foreign reliability management methods and developed a general procedure for managing product reliability performance. This procedure involved developing reliability scorecards and assessing the reliability risk. Using this general procedure, we proposed a framework for the reliability management procedures of weapon systems during development.BRResult: This study developed a reliability scorecard to assess the performance of the reliability activities. The scorecard includes six reliability assessment categories, 21 task areas, and 130 assessment elements. Furthermore, using this scorecard, we present both a quantitative evaluation method and a risk evaluation method for domestic weapon system development projects.BRConclusion: The proposed framework for reliability performance management is highly useful for achieving RAM objectives and assessing the implementation of reliability activities in the development of weapon systems.","PeriodicalId":499683,"journal":{"name":"Sinloeseong eung'yong yeon'gu","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135032389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}